5 min read
Configure AI Models Instead of Hard-Coding Them
Keep model names in configuration, select models by task, and compare routes using the cost of completed work.
Blog posts tagged
AIPage 2
5 min read
The Pull Request Can Now Rewrite Its Own AI Reviewer
Why pull-request-controlled AI review instructions collapse a trust boundary, and how teams can restore it without giving up useful repository context.
5 min read
Kimi K3 Weakens US Control of Frontier AI
Kimi K3's released near-frontier weights reduce dependence on US model providers and make price, deployment control and licence terms more important.
6 min read
Treat AI Like a Colleague, Then Verify Its Work
Delegate clearly, ask for evidence, and build trust in AI output one task at a time.
4 min read
Government Review of AI Models Needs Clear Limits
US review of frontier model releases can reduce specific security risks, but delays need public criteria, time limits and proportionate controls.
9 min read
Apps on Demand: What Happens When Search Can Build the Interface?
A speculative look at AI-generated mini apps, VibeOS, Google Search, and why durable software survives where state, trust, and depth matter.
13 min read
My Current AI Coding Setup
How I use Codex, JetBrains IDEs, Copilot review, AGENTS.md, reusable skills, and CI checks to make AI coding reliable.
9 min read
AI and UK Jobs: Less Apocalypse, More Uneven Reshaping
What current UK evidence says about AI exposure, adoption, entry-level work, and the roles most likely to change.